The xDF-GOG project provides advisory solutions for farmers worldwide, helping them manage weeds and optimize crop protection using advanced drone technology. The entire solution is developed on AWS, leveraging cutting-edge services such as Lambda Functions, Step Functions, Glue, RDS, S3, and AWS Athena to efficiently process and query vast datasets of drone imagery.
As Machine Learning Engineers, we were responsible for developing and maintaining a pipeline flow with drone imagery using AWS Step Functions. Each step in this pipeline involved different tasks, such as batch jobs, Lambda functions, or simple decision-making processes. The pipeline was integrated into the existing Field Management backend service, triggered by farmers uploading drone imagery.
The end result of the pipeline was a set of detailed maps that indicated weed locations, areas to spray, and similar recommendations, which were integrated back into the backend system through a RabbitMQ queue.
This solution has empowered farmers to make data-driven decisions for more precise and efficient weed management, improving crop yields and sustainability.
Tell us your app idea and what you want to achieve. We’ll get back to you in one business day.